{"id":"https://openalex.org/W4408902302","doi":"https://doi.org/10.1145/3676641.3716264","title":"Optimizing Deep Learning Inference Efficiency through Block Dependency Analysis","display_name":"Optimizing Deep Learning Inference Efficiency through Block Dependency Analysis","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408902302","doi":"https://doi.org/10.1145/3676641.3716264"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3716264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3676641.3716264","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072178581","display_name":"Zhanyuan Di","orcid":"https://orcid.org/0000-0003-2716-5051"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhanyuan Di","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2716-5051","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035662158","display_name":"Leping Wang","orcid":"https://orcid.org/0009-0009-4940-5598"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leping Wang","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4940-5598","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027464011","display_name":"En Shao","orcid":"https://orcid.org/0000-0002-9678-7228"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En Shao","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9678-7228","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103571446","display_name":"Zhaojia Ma","orcid":"https://orcid.org/0009-0000-3783-8964"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojia Ma","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4824-9336","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114084654","display_name":"Ziyi Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Ren","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-5821-1163","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583628","display_name":"Hua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Hua","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2198-9304","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093960327","display_name":"Lixian Ma","orcid":"https://orcid.org/0009-0007-1081-0356"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixian Ma","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1081-0356","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000546902","display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0003-2303-9736"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2303-9736","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006750799","display_name":"Guangming Tan","orcid":"https://orcid.org/0000-0002-6361-5948"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6361-5948","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738013","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-1953-1392"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1953-1392","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072178581"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76142604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288056015968323},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6673827171325684},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.647185206413269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5726557970046997},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5385234355926514},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4875630736351013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3957338035106659},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10019281506538391}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288056015968323},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6673827171325684},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.647185206413269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726557970046997},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5385234355926514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4875630736351013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3957338035106659},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10019281506538391},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3716264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676641.3716264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2391829369","display_name":null,"funder_award_id":"Z211100002121143","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6443105322","display_name":null,"funder_award_id":"2021YFB0300202","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7893073575","display_name":null,"funder_award_id":"62032023, T2125013, 62102396, T2422007, U24A20235","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2809290718","https://openalex.org/W2905135312","https://openalex.org/W2961619211","https://openalex.org/W2981758446","https://openalex.org/W3037749908","https://openalex.org/W3095319910","https://openalex.org/W3098625345","https://openalex.org/W3112101075","https://openalex.org/W3119866685","https://openalex.org/W3122286897","https://openalex.org/W3138516171","https://openalex.org/W3170073102","https://openalex.org/W3173358825","https://openalex.org/W3174529902","https://openalex.org/W3191654415","https://openalex.org/W4200150166","https://openalex.org/W4212986322","https://openalex.org/W4220818654","https://openalex.org/W4251637954","https://openalex.org/W4280581786","https://openalex.org/W4287391717","https://openalex.org/W4312938066","https://openalex.org/W4392265896"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W4375867731","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W3122478268","https://openalex.org/W2084758217","https://openalex.org/W408804804","https://openalex.org/W4231021675","https://openalex.org/W3086365953","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Inter-operator":[0],"optimization":[1,91],"in":[2],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"relies":[7],"on":[8],"accurate":[9],"data":[10,20],"dependency":[11,21,62,75],"analysis.":[12,63],"Traditional":[13],"machine":[14],"learning":[15],"compilers":[16],"(MLCs)":[17],"perform":[18],"static":[19],"analysis":[22],"at":[23],"the":[24,66],"element":[25],"and":[26,41,82,98,111,117],"operator":[27],"levels,":[28],"leading":[29],"to":[30,114],"two":[31],"key":[32],"limitations:":[33],"complex":[34,78],"dependencies":[35],"that":[36,45,56,93],"hinder":[37],"efficient":[38],"inter-operator":[39],"optimizations,":[40],"overlooked":[42],"parallelizable":[43],"computations":[44],"underutilize":[46],"GPU":[47,100],"resources.":[48],"We":[49],"introduce":[50],"BlockDepend,":[51],"a":[52],"novel":[53],"MLC":[54],"framework":[55],"addresses":[57],"these":[58],"issues":[59],"through":[60],"block-level":[61,74],"By":[64],"examining":[65],"lower-level":[67],"phases":[68],"of":[69,109],"compilation,":[70],"BlockDepend":[71],"extracts":[72],"crucial":[73],"information,":[76],"simplifying":[77],"relationships":[79],"between":[80],"operators":[81],"uncovering":[83],"hidden":[84],"parallelization":[85],"opportunities.":[86],"This":[87],"allows":[88],"for":[89],"targeted":[90],"strategies":[92],"enhance":[94],"memory":[95],"access":[96],"efficiency":[97],"improve":[99],"utilization.":[101],"Our":[102],"experiments":[103],"demonstrate":[104],"BlockDepend's":[105],"effectiveness,":[106],"achieving":[107],"speedups":[108],"1.71\u00d7":[110],"2.88\u00d7":[112],"compared":[113],"NVIDIA":[115],"TensorRT":[116],"AMD":[118],"MIGraphX,":[119],"respectively,":[120],"across":[121],"various":[122],"workloads.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
